2023.04.03 ArXiv精选
关注领域:
AIGC
3D computer vision learning
Fine-grained learning
GNN
其他
声明
论文较多,时间有限,本专栏无法做文章的讲解,只挑选出符合PaperABC研究兴趣和当前热点问题相关的论文,如果你的research topic和上述内容有关,那本专栏可作为你的论文更新源或Paper reading list.

Paper list:
今日ArXiv共更新85篇
VLP
Towards Flexible Multi-modal Document Models
https://arxiv.org/pdf/2303.18248.pdf

面向文档数据的多模态模型.
DIME-FM : DIstilling Multimodal and Efficient Foundation Models
https://arxiv.org/pdf/2303.18232.pdf

来自Meta的工作.探讨了如何将large的多模态模型高效蒸馏给小的foundation model.
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
https://arxiv.org/pdf/2303.17948.pdf

厦门大学发布的人体climbing数据集,算是一个新坑.